Is Passive Expertise-Based Personalization Enough? A Case Study in AI-Assisted Test-Taking

TL;DR

This study evaluates passive expertise-based personalization in AI assistants for task-oriented dialogues, showing it reduces task load but highlights the need for active personalization to enhance user experience and performance.

Contribution

The paper presents a case study on passive personalization in AI assistants, revealing its benefits and limitations, and advocates for combining active and passive methods for better outcomes.

Findings

Passive personalization reduces task load and improves perception.

Passive methods have task-specific limitations.

Combining active and passive personalization enhances user experience.

Abstract

Novice and expert users have different systematic preferences in task-oriented dialogues. However, whether catering to these preferences actually improves user experience and task performance remains understudied. To investigate the effects of expertise-based personalization, we first built a version of an enterprise AI assistant with passive personalization. We then conducted a user study where participants completed timed exams, aided by the two versions of the AI assistant. Preliminary results indicate that passive personalization helps reduce task load and improve assistant perception, but reveal task-specific limitations that can be addressed through providing more user agency. These findings underscore the importance of combining active and passive personalization to optimize user experience and effectiveness in enterprise task-oriented environments.